One horse. One bet. Every day. Sly Man’s read on the day’s card — the shortlist, the price, and the case for the pick.
Browse the logbookFive horses within half a point of each other — when the model can't split them cleanly, the market becomes the tiebreaker. That's the story today. The engine scanned 402 runners across 36 declared races, working through a four-stage filter pipeline. First, odds: only runners priced between 2.0 and 50.0 decimal survived — no odds-on, no each-way-only shots at long odds. Next, field size: races with fewer than 6 or more than 14 runners were cut, on the logic that small fields are noisy and big fields are chaos. That brought the pool to 169 runners. Finally, three runners were dropped for lay-of-day collision, leaving 166 runners to score. Feature weights put market movement at the top of the dial — 1.6 — ahead of speed at 1.5 and form at 1.2, with class change at 1.0, trainer strike rate and going both at 0.8, and draw at 0.5 (though the draw layer is not yet built and returned unavailable for every runner today).
The day opened with 402 runners across 36 races. The odds band filter cut that to 321 — removing odds-on runners and anything priced beyond 50.0 decimal. The field-size filter reduced the pool further to 169, keeping only races with 6–14 declared runners. Three runners then fell at the lay-of-day collision check, leaving 166 runners in contention for the composite ranking.
The top of the board is tight — uncomfortably so. Ronnie Russet leads with a composite of 7.60/10, driven by a speed z-score of +1.75 against the field mean and a market move that steamed in without a single bookmaker drifting. Soldiers Trick sits second at 7.44/10, with a form score of +3.00 off a recent winning run, though the speed edge over the field is modest at +0.59. Check The Score comes third at 7.41/10 — the speed figure is the standout on the shortlist at z = +2.24, and the market has come in hard, but Fergal O'Brien's trainer strike rate at 8% over the last 30 days offers no support. To Chase A Dream scores 7.22/10 at Class 2, with a hot trainer in John Dawson at 27% over 30 days — the same read as Ronnie Russet's handler, Jedd O'Keeffe. The gap between first and fifth on this list is just 0.65 points; the gap between first and the selection is 0.65 points too, because the selection, Marco Du Seuil, sits sixth at 6.95/10. The engine's tiebreaker rule applies when the leader's margin is under 0.4 — Ronnie Russet leads by only 0.16 over second place, well inside that threshold. When scores cannot separate them, the bet goes to the shortest price on the list: the horse the market rates likeliest. That's Marco Du Seuil at 11/8. If you're drawn to the longer end of today's shortlist, Golden Splendour at 11/1 is the value pick published separately — not today's selection, but the longest price on the board with a composite of 7.08/10.
The read I keep coming back to with Marco Du Seuil is that the market is doing something the composite score doesn't fully capture. This is a horse sitting at 11/8 — the shortest price on the entire shortlist — in a maiden hurdle at Cork, and the majority of bookmakers shortened without a single one going the other way. That's a steamer signal, and it carries the highest feature weight in the model at 1.6. The market implied probability is 37.6%, and the engine's estimated win probability comes in at 35.4% — unusually, that's a slight negative edge of -16.0%, which means the model thinks the market has already priced this one correctly, or even slightly over-baked it. I'd rather be honest about that than dress it up.
What the composite does credit is the speed figure: an SR of 156 against a field mean of 127.1 gives a z-score of +1.24, weighted at 1.5 in the model. That's a genuine speed advantage — the horse has shown enough raw pace to stand out in this field. Form reads '1-23', with the decay-weighted average sitting at +1.00 — solid rather than spectacular, but a winning run is in there and the model sees it. Gordon Elliott's trainer strike rate at 11% over the last 30 days is on par with the norm, offering no uplift, but also no red flag. The going feature returned a nominal +0.10 — one run on good or adjacent going, placed, so there's at least a tick in that box where several rivals couldn't score at all.
The selection logic is explicit here and I'm not going to soften it: Marco Du Seuil is today's bet because the scores at the top of the shortlist are locked within a margin too narrow to call, and the tiebreaker — shortest price on the list — lands here. Ronnie Russet has the top composite. The market, though, has converged most heavily on Marco Du Seuil, and at 11/8 the model is following that.
The negative model edge of -16.0% is the most honest risk on the card today — the engine thinks the market has already fully priced this horse, possibly beyond its true probability, which is an unusual position for a selection. The going feature is wafer-thin: one run on good or adjacent ground, placed, but that's the full data set — no career pattern to lean on. Class is listed as unspecified for today's race, so the class-change feature returned unavailable, meaning any step up or down in grade is invisible to the model. Gordon Elliott's 9% trainer strike rate over the last 30 days is on par, not hot — there's no trainer momentum behind this one. And finally, the tiebreaker mechanism itself carries its own risk: this is not the top-scoring horse today — Ronnie Russet holds that position at 7.60/10 — so anyone who prefers to follow the composite leader rather than the market tiebreaker has a legitimate reason to do so.
Marco Du Seuil · 11/8 · 1 unit · MEDIUM
The Fox’s Wire · Bet of the Day
The algorithm pulled five contenders from today’s card. One earned the ticket — the rest are what it beat. When each race settles, the finishes fill in so you can judge the shortlist, not just the selection.
Position only — payout-neutral. A process check, not a P/L. Click any horse to read its profile.
Value pick 4 of 24 won · +6.83 units at advised prices · since 11 October 2026. Kept separate from the bet’s record above.
